ln-41-test-strategy-planner
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process a wide variety of untrusted external data sources, creating a surface for indirect prompt injection attacks.
- Ingestion points: As described in the 'Tool Routing' and 'Checklist' sections of
SKILL.md, the agent reads requirements, repository files, git state, language server data, CI reports, and external documentation (advisories, specifications). - Boundary markers: The skill lacks explicit boundary delimiters or 'ignore embedded instructions' warnings for the data it processes. However, it does instruct the agent to 'ask one concise question only when different interpretations materially change the strategy,' which provides a minimal human-in-the-loop checkpoint.
- Capability inventory: The skill utilizes read-only capabilities including native file reads, Git commands, language server queries, and searching repository manifests.
- Sanitization: No specific sanitization, escaping, or validation logic is defined for the external content before it is processed by the LLM.
Audit Metadata